Researchers have recently achieved significant advances in deep learning techniques,
which in turn has substantially advanced other research disciplines, such as natural …

Abstract Large Language Models (LLMs) have recently gained significant attention due to
their remarkable capabilities in performing diverse tasks across various domains. However …

This technical report presents AutoGen, a new framework that enables development of LLM
applications using multiple agents that can converse with each other to solve tasks. AutoGen …

Large language models (LLMs) have shown promise in proving formal theorems using proof
assistants such as Lean. However, existing methods are difficult to reproduce or build on …

As one of the most advanced techniques in AI, Retrieval-Augmented Generation (RAG) can
offer reliable and up-to-date external knowledge, providing huge convenience for numerous …

Large language models (LLMs) pretrained on vast source code have achieved prominent
progress in code intelligence. However, existing code LLMs have two main limitations in …

Recently, the ChatGPT LLM has received great attention: it can be used as a bot for
discussing source code, prompting it to suggest changes, provide descriptions or even …

Large language models (LLMs) demonstrate impressive capabilities to generate accurate
code snippets given natural language intents in a zero-shot manner, ie, without the need for …

Pre-trained Generative Language models (eg, PLBART, CodeT5, SPT-Code) for source
code yielded strong results on several tasks in the past few years, including code generation …

With direct access to human-written reference as memory, retrieval-augmented generation
has achieved much progress in a wide range of text generation tasks. Since better memory …